With the rapid advances in remote-sensing technologies and the larger number of satellite images, fast and effective object detection plays an important role in understanding and analyzing image information, which could be further applied to civilian and military fields. Recently object detection methods with region-based convolutional neural network have shown excellent performance. However, these two-stage methods contain region proposal generation and object detection procedures, resulting in low computation speed. Because of the expensive manual costs, the quantity of well-annotated aerial images is scarce, which also limits the progress of geospatial object detection in remote sensing. In this paper, on the one hand, we construct and release a large-scale remote-sensing dataset for geospatial object detection (RSD-GOD) that consists of 5 different categories with 18,187 annotated images and 40,990 instances. On the other hand, we design a single shot detection framework with multi-scale feature fusion. The feature maps from different layers are fused together through the up-sampling and concatenation blocks to predict the detection results. High-level features with semantic information and low-level features with fine details are fully explored for detection tasks, especially for small objects. Meanwhile, a soft non-maximum suppression strategy is put into practice to select the final detection results. Extensive experiments have been conducted on two datasets to evaluate the designed network. Results show that the proposed approach achieves a good detection performance and obtains the mean average precision value of 89.0% on a newly constructed RSD-GOD dataset and 83.8% on the Northwestern Polytechnical University very high spatial resolution-10 (NWPU VHR-10) dataset at 18 frames per second (FPS) on a NVIDIA GTX-1080Ti GPU.

Remote sensing image captioning (RSIC) has great significance in image understanding, which describes the image content in natural language. Existing methods are mainly based on deep learning and rely on the encoder–decoder model to generate sentences. In the decoding process, recurrent neural network (RNN) and long short-term memory (LSTM) are normally applied to sequentially generate image captions. In this letter, the transformer encoder–decoder is combined with grid features to improve the RSIC performance. First, the pretrained convolutional neural network (CNN) is used to extract grid-based visual features, which are encoded as vectorial representations. Then, the transformer outputs semantic descriptions to bridge visual features and natural language. Besides, the self-critical sequence training (SCST) strategy is applied to further optimize the image captioning model and improve the quality of generated sentences. Extensive experiments are organized on three public datasets of RSCID, UCM-Captions, and Sydney-Captions. Experimental results demonstrate the effectiveness of SCST strategy and the proposed method achieves superior performance compared with the state-of-the-art image captioning approaches on the RSCID dataset.

In weather forecasting, numerical weather prediction (NWP) that is based on physical models requires proper post-processing before it can be applied to actual operations. Therefore, research on intelligent post-processing algorithms has always been an important topic in this field. This paper proposes a model output deep learning (MODL) method for post-processing, which can improve the forecast effect of numerical weather prediction. MODL is an end-to-end post-processing method based on deep convolutional neural network, which directly learns the mapping relationship between the forecast fields output by numerical model and the observation temperature field in order to obtain more accurate temperature forecasts. MODL modifies the existing deep convolution model according to the post-processing problem’s characteristics, thereby improving the performance of the weather forecast. This paper uses The International Grand Global Ensemble (TIGGE) dataset from European Centre for Medium-Range Weather Forecasts (ECMWF) and the observed air temperature of 2 m obtained from Tianjin meteorological station in order to test the post-processing performance of MODL. The MODL method applied to temperature in post-processing is compared with the ECMWF forecast, Model Output Statistics (MOS) methods, and Model Output Machine Learning (MOML) methods. The Root Mean Square Error (RMSE) of the temperature field predicted by MODL and the observed temperature field is smaller than the other models and the accuracy of the temperature difference of 2 °C (Acc) is higher, especially where the prediction time is in the first three days. The lightweight nature of MODL also makes it suitable for most operations.

Tropical cyclone (TC) intensity estimation is critical for disaster forecasting and severe weather warning. In recent years, the performance of various TC intensity estimation models has been gradually enhanced, but the accuracy still needs to be improved. In this article, 71 intensity-related features are extracted from satellite infrared images of TCs. These features are grouped by eye features, circle features, texture features, and time-series features. Using the random forest model as the underlying algorithm of conformal prediction (CP), an intensity applicable CP framework is proposed. On the one hand, the proposed network can achieve point estimation of the TC intensity. On the other hand, it is also possible to realize the intensity interval estimation that satisfies a given significance level. In the experiments, the root mean square error of the point estimation algorithm is 7.86 kt (1 kt ≈ 0.51 m/s), and the performance of the proposed algorithm is better than the comparison algorithms. In addition, interval estimation enriches decision-making information. The experimental results show that the proposed model is a competitive and promising method for estimating the TC intensity.

The number of leaves in maize plant is one of the key traits describing its growth conditions. It is directly related to plant development and leaf counts also give insight into changing plant development stages. Compared with the traditional solutions which need excessive human interventions, the methods of computer vision and machine learning are more efficient. However, leaf counting with computer vision remains a challenging problem. More and more researchers are trying to improve accuracy. To this end, an automated, deep learning based approach for counting leaves in maize plants is developed in this paper. A Convolution Neural Network(CNN) is used to extract leaf features. The CNN model in this paper is inspired by Google Inception Net V3, which using multi-scale convolution kernels in one convolution layer. To compress feature maps generated from some middle layers in CNN, the Fisher Vector (FV) is used to reduce redundant information. Finally, these encoded feature maps are used to regress the leaf numbers by using Random Forests. To boost the related research, a relatively single maize image dataset (Different growth stage with 2845 samples, which 80% for train and 20% for test) is constructed by our team. The proposed algorithm in single maize data set achieves Mean Square Error (MSE) of 0.32.